This is essentially a fork of Yida's original repo found here. Below is his original README.
The work that I did during the Summer of 2022, which I will admit now is very messy, which can be found in the ./dev directory.
The code in this repository is an implementation of CLAS-FV framework described in the paper, "Fully automated multi-heartbeat echocardiography video segmentation and motion tracking," SPIE Medical Imaging 2022.
motion_segment.py: The main script for segmenting an echocardiography video with or without fusion augmentation.
Example usage: python motion_segment.py -p <path to the ultrasound video file> -d cuda -c all
echonet_r2plus1d_notebooks: Notebooks for training and validating our CLAS-FV framework
src: Source codes
Pretrained Model Weights is available here: https://drive.google.com/drive/folders/1NZ4A7hjfiztb-ud0IP4JahVn1EcMYDsP?usp=sharing.
If you use our code in your work or you find it useful, please cite the article below (or see our bibtex):
Chen, Yida, Xiaoyan Zhang, Christopher M. Haggerty, and Joshua V. Stough. "Fully automated multi-heartbeat echocardiography video segmentation and motion tracking." In Medical Imaging 2022: Image Processing. International Society for Optics and Photonics, 2022.
The project is released under the MIT license. The code has not been tested for any medical applications.